Computerized Medical Imaging and Graphics
Volume 36, Issue 1 , Pages 25-37 , January 2012

Left ventricular myocardium segmentation on arterial phase of multi-detector row computed tomography

  • I-Chen Tsai

      Affiliations

    • Department of Radiology, Taichung Veterans General Hospital, Taichung, Taiwan
    • Institute of Clinical Medicine, National Yang Ming University, Taiwan
  • ,
  • Yu-Len Huang

      Affiliations

    • Department of Computer Science, Tunghai University, Taichung 407, Taiwan
    • Corresponding Author InformationCorresponding author. Tel.: +886 4 23590121x33800; fax: +886 4 23591567.
  • ,
  • Kai-Hua Kuo

      Affiliations

    • Department of Computer Science, Tunghai University, Taichung 407, Taiwan

Received 25 November 2009 ,Revised 23 July 2010 ,Accepted 18 March 2011.

  • Image Result

    The horizontal long axis and short axis images from apex to base of LV.

    The horizontal long axis and short axis images from apex to base of LV.

  • Image Result

    The proposed segmentation for the middle-ventricle slice on an MDCT imaging: (a) original image, (b) preprocessed image, (c) result of the region growing process, (d) the extracted endocardial contour

    The proposed segmentation for the middle-ventricle slice on an MDCT imaging: (a) original image, (b) preprocessed image, (c) result of the region growing process, (d) the extracted endocardial contour, (e) the extracted epicardial contour and (f) the formed ROI.

  • Image Result
    Flowchart of the proposed scheme for auto-segmentation of LV on MDCT imaging.

    Flowchart of the proposed scheme for auto-segmentation of LV on MDCT imaging.

  • Image Result
    Results of the anisotropic diffusion de-nosing: (a) de-nosed result of Fig. 2(a), (b) difference image (enhanced by logarithm transformation) between Figs. 2(a) and 4(a).

    Results of the anisotropic diffusion de-nosing: (a) de-nosed result of Fig. 2(a), (b) difference image (enhanced by logarithm transformation) between Figs. 2(a) and 4(a).

  • Image Result
    Histograms of (a) original image and (b) the intensity transformed image.

    Histograms of (a) original image and (b) the intensity transformed image.

  • Image Result
    Automatic seed searching: (a) binary image that generated by thresholding on the enhanced image, (b) the speckle removed image (using the erosion operator) and (c) located seed from the biggest region

    Automatic seed searching: (a) binary image that generated by thresholding on the enhanced image, (b) the speckle removed image (using the erosion operator) and (c) located seed from the biggest region near the centroid of image.

  • Image Result
    A comparison of the endocardial and epicardial contours: (a) the endocardial contour generated by region growing and (b) the improved contours using the convex hull algorithm.

    A comparison of the endocardial and epicardial contours: (a) the endocardial contour generated by region growing and (b) the improved contours using the convex hull algorithm.

  • Image Result
    Inappropriate segmentations by using (a) region growing method and (b) level-set segmentation.

    Inappropriate segmentations by using (a) region growing method and (b) level-set segmentation.

  • Image Result
    Propagation term controls contour motion, a positive value of P forces the contour to expand.

    Propagation term controls contour motion, a positive value of P forces the contour to expand.

  • Image Result
    Comparison of an automated contouring area (SEG) with the manual contouring area (REF), with (overlap) the correctly segmented pixels (extra) the false positives and (miss) the false negatives.

    Comparison of an automated contouring area (SEG) with the manual contouring area (REF), with (overlap) the correctly segmented pixels (extra) the false positives and (miss) the false negatives.

  • Image Result
    Automatic contouring results (Case#1) by using the proposed method.

    Automatic contouring results (Case#1) by using the proposed method.

  • Image Result
    Manual sketched contours (Case#1) by Expert#1.

    Manual sketched contours (Case#1) by Expert#1.

  • Image Result
    (a) Scatter plot of the automatic segmentation (SEG) against the mean of manual segmentation from two experts (REF) for all datasets and (b) cumulative distribution of error distance between manual co

    (a) Scatter plot of the automatic segmentation (SEG) against the mean of manual segmentation from two experts (REF) for all datasets and (b) cumulative distribution of error distance between manual contours and the automatically segmented contours.

  • Image Result
    (a) An unsatisfied contour generated by the proposed method and (b) the contour delineated by experts.

    (a) An unsatisfied contour generated by the proposed method and (b) the contour delineated by experts.

  • Image Result
    Contours generated by the LSM (solid line) and the region growing method (dotted line).

    Contours generated by the LSM (solid line) and the region growing method (dotted line).

PII: S0895-6111(11)00046-2

doi: 10.1016/j.compmedimag.2011.03.003

Computerized Medical Imaging and Graphics
Volume 36, Issue 1 , Pages 25-37 , January 2012